Self-Knowledge Distillation via Feature Enhancement for Speaker Verification

Liu, Bei; Wang, Haoyu; Chen, Zhengyang; Wang, Shuai; Ye, Qian

doi:10.1109/icassp43922.2022.9746529

Cited by 19 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, some researchers applied the techniques of Knowledge Distillation (KD) [46], [47] and Neural Architecture Search (NAS) [48] to implement lightweight SV [49]- [52]. In the work of [49], the strategy of teacher-student training was proposed for text-independent SV, and competitive error rate with 88-93% smaller models was obtained.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Speaker Identification Using Lightweight Prototypical Network With Feature Grouping and Interaction

Chen

Cao

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Although many efforts have been made on decreasing the model complexity for speaker verification, it is still challenging to deploy speaker verification systems with satisfactory result on low-resource terminals. We design a transformation module that performs feature partition and fusion to implement lightweight speaker verification. The transformation module consists of multiple simple but effective operations, such as convolution, pooling, mean, concatenation, normalization, and element-wise summation. It works in a plug-and-play way, and can be easily implanted into a wide variety of models to reduce the model complexity while maintaining the model error. First, the input feature is split into several low-dimensional feature subsets for decreasing the model complexity. Then, each feature subset is updated by fusing it with the inter-feature-subsets correlational information to enhance its representational capability. Finally, the updated feature subsets are independently fed into the block (one or several layers) of the model for further processing. The features that are output from current block of the model are processed according to the steps above before they are fed into the next block of the model. Experimental data are selected from two public speech corpora (namely VoxCeleb1 and VoxCeleb2). Results show that implanting the transformation module into three models (namely AMCRN, ResNet34, and ECAPA-TDNN) for speaker verification slightly increases the model error and significantly decreases the model complexity. Our proposed method outperforms baseline methods on the whole in memory requirement and computational complexity with lower equal error rate. It also generalizes well across truncated segments with various lengths.

show abstract